1
|
Bazoge A, Morin E, Daille B, Gourraud PA. Applying Natural Language Processing to Textual Data From Clinical Data Warehouses: Systematic Review. JMIR Med Inform 2023; 11:e42477. [PMID: 38100200 PMCID: PMC10757232 DOI: 10.2196/42477] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Revised: 01/16/2023] [Accepted: 09/07/2023] [Indexed: 12/17/2023] Open
Abstract
BACKGROUND In recent years, health data collected during the clinical care process have been often repurposed for secondary use through clinical data warehouses (CDWs), which interconnect disparate data from different sources. A large amount of information of high clinical value is stored in unstructured text format. Natural language processing (NLP), which implements algorithms that can operate on massive unstructured textual data, has the potential to structure the data and make clinical information more accessible. OBJECTIVE The aim of this review was to provide an overview of studies applying NLP to textual data from CDWs. It focuses on identifying the (1) NLP tasks applied to data from CDWs and (2) NLP methods used to tackle these tasks. METHODS This review was performed according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We searched for relevant articles in 3 bibliographic databases: PubMed, Google Scholar, and ACL Anthology. We reviewed the titles and abstracts and included articles according to the following inclusion criteria: (1) focus on NLP applied to textual data from CDWs, (2) articles published between 1995 and 2021, and (3) written in English. RESULTS We identified 1353 articles, of which 194 (14.34%) met the inclusion criteria. Among all identified NLP tasks in the included papers, information extraction from clinical text (112/194, 57.7%) and the identification of patients (51/194, 26.3%) were the most frequent tasks. To address the various tasks, symbolic methods were the most common NLP methods (124/232, 53.4%), showing that some tasks can be partially achieved with classical NLP techniques, such as regular expressions or pattern matching that exploit specialized lexica, such as drug lists and terminologies. Machine learning (70/232, 30.2%) and deep learning (38/232, 16.4%) have been increasingly used in recent years, including the most recent approaches based on transformers. NLP methods were mostly applied to English language data (153/194, 78.9%). CONCLUSIONS CDWs are central to the secondary use of clinical texts for research purposes. Although the use of NLP on data from CDWs is growing, there remain challenges in this field, especially with regard to languages other than English. Clinical NLP is an effective strategy for accessing, extracting, and transforming data from CDWs. Information retrieved with NLP can assist in clinical research and have an impact on clinical practice.
Collapse
Affiliation(s)
- Adrien Bazoge
- Nantes Université, École Centrale Nantes, CNRS, LS2N, UMR 6004, F-44000 Nantes, France
- Nantes Université, CHU de Nantes, Pôle Hospitalo-Universitaire 11: Santé Publique, Clinique des données, INSERM, CIC 1413, F-44000 Nantes, France
| | - Emmanuel Morin
- Nantes Université, École Centrale Nantes, CNRS, LS2N, UMR 6004, F-44000 Nantes, France
| | - Béatrice Daille
- Nantes Université, École Centrale Nantes, CNRS, LS2N, UMR 6004, F-44000 Nantes, France
| | - Pierre-Antoine Gourraud
- Nantes Université, CHU de Nantes, Pôle Hospitalo-Universitaire 11: Santé Publique, Clinique des données, INSERM, CIC 1413, F-44000 Nantes, France
- Nantes Université, INSERM, CHU de Nantes, École Centrale Nantes, Centre de Recherche Translationnelle en Transplantation et Immunologie, CR2TI, F-44000 Nantes, France
| |
Collapse
|
2
|
Lai PT, Wei CH, Luo L, Chen Q, Lu Z. BioREx: Improving biomedical relation extraction by leveraging heterogeneous datasets. J Biomed Inform 2023; 146:104487. [PMID: 37673376 DOI: 10.1016/j.jbi.2023.104487] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Revised: 08/18/2023] [Accepted: 09/02/2023] [Indexed: 09/08/2023]
Abstract
Biomedical relation extraction (RE) is the task of automatically identifying and characterizing relations between biomedical concepts from free text. RE is a central task in biomedical natural language processing (NLP) research and plays a critical role in many downstream applications, such as literature-based discovery and knowledge graph construction. State-of-the-art methods were used primarily to train machine learning models on individual RE datasets, such as protein-protein interaction and chemical-induced disease relation. Manual dataset annotation, however, is highly expensive and time-consuming, as it requires domain knowledge. Existing RE datasets are usually domain-specific or small, which limits the development of generalized and high-performing RE models. In this work, we present a novel framework for systematically addressing the data heterogeneity of individual datasets and combining them into a large dataset. Based on the framework and dataset, we report on BioREx, a data-centric approach for extracting relations. Our evaluation shows that BioREx achieves significantly higher performance than the benchmark system trained on the individual dataset, setting a new SOTA from 74.4% to 79.6% in F-1 measure on the recently released BioRED corpus. We further demonstrate that the combined dataset can improve performance for five different RE tasks. In addition, we show that on average BioREx compares favorably to current best-performing methods such as transfer learning and multi-task learning. Finally, we demonstrate BioREx's robustness and generalizability in two independent RE tasks not previously seen in training data: drug-drug N-ary combination and document-level gene-disease RE. The integrated dataset and optimized method have been packaged as a stand-alone tool available at https://github.com/ncbi/BioREx.
Collapse
Affiliation(s)
- Po-Ting Lai
- National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894 Bethesda, USA
| | - Chih-Hsuan Wei
- National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894 Bethesda, USA
| | - Ling Luo
- School of Computer Science and Technology, Dalian University of Technology, 116024 Dalian, China
| | - Qingyu Chen
- National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894 Bethesda, USA
| | - Zhiyong Lu
- National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894 Bethesda, USA.
| |
Collapse
|
3
|
Davis SE, Zabotka L, Desai RJ, Wang SV, Maro JC, Coughlin K, Hernández-Muñoz JJ, Stojanovic D, Shah NH, Smith JC. Use of Electronic Health Record Data for Drug Safety Signal Identification: A Scoping Review. Drug Saf 2023; 46:725-742. [PMID: 37340238 DOI: 10.1007/s40264-023-01325-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 05/31/2023] [Indexed: 06/22/2023]
Abstract
INTRODUCTION Pharmacovigilance programs protect patient health and safety by identifying adverse event signals through postmarketing surveillance of claims data and spontaneous reports. Electronic health records (EHRs) provide new opportunities to address limitations of traditional approaches and promote discovery-oriented pharmacovigilance. METHODS To evaluate the current state of EHR-based medication safety signal identification, we conducted a scoping literature review of studies aimed at identifying safety signals from routinely collected patient-level EHR data. We extracted information on study design, EHR data elements utilized, analytic methods employed, drugs and outcomes evaluated, and key statistical and data analysis choices. RESULTS We identified 81 eligible studies. Disproportionality methods were the predominant analytic approach, followed by data mining and regression. Variability in study design makes direct comparisons difficult. Studies varied widely in terms of data, confounding adjustment, and statistical considerations. CONCLUSION Despite broad interest in utilizing EHRs for safety signal identification, current efforts fail to leverage the full breadth and depth of available data or to rigorously control for confounding. The development of best practices and application of common data models would promote the expansion of EHR-based pharmacovigilance.
Collapse
Affiliation(s)
- Sharon E Davis
- Department of Biomedical Informatics, Vanderbilt University Medical Center, 2525 West End Ave, Suite 1475, Nashville, TN, 37203, USA
- Vanderbilt University School of Medicine, Nashville, TN, USA
| | | | - Rishi J Desai
- Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
| | - Shirley V Wang
- Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
| | - Judith C Maro
- Harvard Medical School, Boston, MA, USA
- Harvard Pilgrim Health Care Institute, Boston, MA, USA
| | | | | | | | - Nigam H Shah
- School of Medicine, Stanford University, Stanford, CA, USA
- Stanford Health Care, Palo Alto, CA, USA
| | - Joshua C Smith
- Department of Biomedical Informatics, Vanderbilt University Medical Center, 2525 West End Ave, Suite 1475, Nashville, TN, 37203, USA.
- Vanderbilt University School of Medicine, Nashville, TN, USA.
| |
Collapse
|
4
|
Lai PT, Wei CH, Luo L, Chen Q, Lu Z. BioREx: Improving Biomedical Relation Extraction by Leveraging Heterogeneous Datasets. ARXIV 2023:arXiv:2306.11189v1. [PMID: 37502629 PMCID: PMC10370213] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Indexed: 07/29/2023]
Abstract
Biomedical relation extraction (RE) is the task of automatically identifying and characterizing relations between biomedical concepts from free text. RE is a central task in biomedical natural language processing (NLP) research and plays a critical role in many downstream applications, such as literature-based discovery and knowledge graph construction. State-of-the-art methods were used primarily to train machine learning models on individual RE datasets, such as protein-protein interaction and chemical-induced disease relation. Manual dataset annotation, however, is highly expensive and time-consuming, as it requires domain knowledge. Existing RE datasets are usually domain-specific or small, which limits the development of generalized and high-performing RE models. In this work, we present a novel framework for systematically addressing the data heterogeneity of individual datasets and combining them into a large dataset. Based on the framework and dataset, we report on BioREx, a data-centric approach for extracting relations. Our evaluation shows that BioREx achieves significantly higher performance than the benchmark system trained on the individual dataset, setting a new SOTA from 74.4% to 79.6% in F-1 measure on the recently released BioRED corpus. We further demonstrate that the combined dataset can improve performance for five different RE tasks. In addition, we show that on average BioREx compares favorably to current best-performing methods such as transfer learning and multi-task learning. Finally, we demonstrate BioREx's robustness and generalizability in two independent RE tasks not previously seen in training data: drug-drug N-ary combination and document-level gene-disease RE. The integrated dataset and optimized method have been packaged as a stand-alone tool available at https://github.com/ncbi/BioREx.
Collapse
Affiliation(s)
- Po-Ting Lai
- National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894, Bethesda, USA
| | - Chih-Hsuan Wei
- National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894, Bethesda, USA
| | - Ling Luo
- School of Computer Science and Technology, Dalian University of Technology, 116024, Dalian, China
| | - Qingyu Chen
- National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894, Bethesda, USA
| | - Zhiyong Lu
- National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894, Bethesda, USA
| |
Collapse
|
5
|
Malec SA, Taneja SB, Albert SM, Elizabeth Shaaban C, Karim HT, Levine AS, Munro P, Callahan TJ, Boyce RD. Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: A use case studying depression as a risk factor for Alzheimer's disease. J Biomed Inform 2023; 142:104368. [PMID: 37086959 PMCID: PMC10355339 DOI: 10.1016/j.jbi.2023.104368] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2022] [Revised: 03/03/2023] [Accepted: 04/17/2023] [Indexed: 04/24/2023]
Abstract
BACKGROUND Causal feature selection is essential for estimating effects from observational data. Identifying confounders is a crucial step in this process. Traditionally, researchers employ content-matter expertise and literature review to identify confounders. Uncontrolled confounding from unidentified confounders threatens validity, conditioning on intermediate variables (mediators) weakens estimates, and conditioning on common effects (colliders) induces bias. Additionally, without special treatment, erroneous conditioning on variables combining roles introduces bias. However, the vast literature is growing exponentially, making it infeasible to assimilate this knowledge. To address these challenges, we introduce a novel knowledge graph (KG) application enabling causal feature selection by combining computable literature-derived knowledge with biomedical ontologies. We present a use case of our approach specifying a causal model for estimating the total causal effect of depression on the risk of developing Alzheimer's disease (AD) from observational data. METHODS We extracted computable knowledge from a literature corpus using three machine reading systems and inferred missing knowledge using logical closure operations. Using a KG framework, we mapped the output to target terminologies and combined it with ontology-grounded resources. We translated epidemiological definitions of confounder, collider, and mediator into queries for searching the KG and summarized the roles played by the identified variables. We compared the results with output from a complementary method and published observational studies and examined a selection of confounding and combined role variables in-depth. RESULTS Our search identified 128 confounders, including 58 phenotypes, 47 drugs, 35 genes, 23 collider, and 16 mediator phenotypes. However, only 31 of the 58 confounder phenotypes were found to behave exclusively as confounders, while the remaining 27 phenotypes played other roles. Obstructive sleep apnea emerged as a potential novel confounder for depression and AD. Anemia exemplified a variable playing combined roles. CONCLUSION Our findings suggest combining machine reading and KG could augment human expertise for causal feature selection. However, the complexity of causal feature selection for depression with AD highlights the need for standardized field-specific databases of causal variables. Further work is needed to optimize KG search and transform the output for human consumption.
Collapse
Affiliation(s)
- Scott A Malec
- Department of Biomedical Informatics, School of Medicine, University of Pittsburgh, Pittsburgh, PA, USA
| | - Sanya B Taneja
- Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA
| | - Steven M Albert
- Department of Behavioral and Community Health Sciences, School of Public Health, University of Pittsburgh, Pittsburgh, PA, USA
| | - C Elizabeth Shaaban
- Department of Epidemiology, School of Public Health, University of Pittsburgh, Pittsburgh, PA, USA
| | - Helmet T Karim
- Department of Psychiatry, University of Pittsburgh, Pittsburgh, PA, USA; Department of Bioengineering, University of Pittsburgh, Pittsburgh, PA, USA
| | - Arthur S Levine
- Department of Neurobiology, School of Medicine, University of Pittsburgh, Pittsburgh, PA, USA; The Brain Institute, School of Medicine, University of Pittsburgh, Pittsburgh, PA, USA
| | - Paul Munro
- School of Computing and Information, University of Pittsburgh, Pittsburgh, PA, USA
| | - Tiffany J Callahan
- Department of Biomedical Informatics, Columbia University, New York, NY, USA
| | - Richard D Boyce
- Department of Biomedical Informatics, School of Medicine, University of Pittsburgh, Pittsburgh, PA, USA; Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA
| |
Collapse
|
6
|
Zhao Y, Yu Y, Wang H, Li Y, Deng Y, Jiang G, Luo Y. Machine Learning in Causal Inference: Application in Pharmacovigilance. Drug Saf 2022; 45:459-476. [PMID: 35579811 PMCID: PMC9114053 DOI: 10.1007/s40264-022-01155-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/09/2022] [Indexed: 01/28/2023]
Abstract
Monitoring adverse drug events or pharmacovigilance has been promoted by the World Health Organization to assure the safety of medicines through a timely and reliable information exchange regarding drug safety issues. We aim to discuss the application of machine learning methods as well as causal inference paradigms in pharmacovigilance. We first reviewed data sources for pharmacovigilance. Then, we examined traditional causal inference paradigms, their applications in pharmacovigilance, and how machine learning methods and causal inference paradigms were integrated to enhance the performance of traditional causal inference paradigms. Finally, we summarized issues with currently mainstream correlation-based machine learning models and how the machine learning community has tried to address these issues by incorporating causal inference paradigms. Our literature search revealed that most existing data sources and tasks for pharmacovigilance were not designed for causal inference. Additionally, pharmacovigilance was lagging in adopting machine learning-causal inference integrated models. We highlight several currently trending directions or gaps to integrate causal inference with machine learning in pharmacovigilance research. Finally, our literature search revealed that the adoption of causal paradigms can mitigate known issues with machine learning models. We foresee that the pharmacovigilance domain can benefit from the progress in the machine learning field.
Collapse
Affiliation(s)
- Yiqing Zhao
- Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, 750 N Lake Shore Drive, Room 11-189, Chicago, IL, 60611, USA
| | - Yue Yu
- Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, 55902, USA
| | - Hanyin Wang
- Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, 750 N Lake Shore Drive, Room 11-189, Chicago, IL, 60611, USA
| | - Yikuan Li
- Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, 750 N Lake Shore Drive, Room 11-189, Chicago, IL, 60611, USA
| | - Yu Deng
- Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, 750 N Lake Shore Drive, Room 11-189, Chicago, IL, 60611, USA
| | - Guoqian Jiang
- Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, 55902, USA
| | - Yuan Luo
- Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, 750 N Lake Shore Drive, Room 11-189, Chicago, IL, 60611, USA.
| |
Collapse
|